Table 2 Model Fit Indices for 1 to 7 Classes of Parallel Latent Growth Model of PHQ-9 and GAD-7 Trajectories
From: Two-way messaging therapy for depression and anxiety: longitudinal response trajectories
| Â | 1-class | 2-classes | 3-classes | 4-classes | 5-classes | 6-classes | 7-classes |
|---|---|---|---|---|---|---|---|
Akaike Information Criteria | 346,037.34 | 330,711.31 | 327,235.57 | 325,672.71 | 324,545.30 | 323,369.51 | 322,410.85 |
Bayesian Information Criteria | 346,153.81 | 330,936.98 | 327,512.20 | 326,000.30 | 324,923.84 | 323,799.02 | 322,891.31 |
Sample-Size Adjusted BIC | 346,102.97 | 330,838.46 | 327,391.44 | 325,857.30 | 324,758.59 | 323,611.52 | 322,681.57 |
Entropy | – | .79 | .72 | .71 | 0.67 | .71 | .71 |
Lo-Mendell-Rubin Adjusted LRT | – | 15,030.40 | 3436.82 | 1552.94 | 1124.11 | 1171.74 | 957.91 |
P-value | – | <.001 | <.001 | .018 | <.001 | <.001 | .264 |
Bootsrapped LRT P-value | – | <.001 | <.001 | <.001 | <.001 | <.001 | <.001 |